© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 104223
    Prev
    Next
    INDEX
    Explanations

    proper names and titles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     $
    -1.31
    ;
    -1.30
    当你
    -1.24
    Após
    -1.23
    Wanneer
    -1.22
    當中
    -1.19
    卧槽
    -1.17
    Fig
    -1.17
    unggu
    -1.16
     OGSÅ
    -1.15
    POSITIVE LOGITS
     other
    1.45
     otros
    1.38
    %%%%%%%%%
    1.38
    yeon
    1.30
    Generalized
    1.30
    %%%%%%%
    1.28
     others
    1.24
     anderen
    1.23
     skolen
    1.21
    殤
    1.20
    Activations Density 0.130%

    No Known Activations